question

What is the difference between measured and manipulated variables?

answer

Manipulated variables (IV) are what is changed while measured variables (DV) are the observed results

question

What is selection bias and how does that effect internal validity?

answer

This can occur when you do not randomly assign individuals to a certain group. Effects internal validity because there could have been another reason that the results ended the way that they did.

question

What is reactivity or the Hawthorne Effect?

answer

The alteration of behavior by the subjects of a study due to their awareness of being observed.

question

What are the IV, DV, and CV in the Elliot color example?

answer

Independent: manipulated ink color with levels Dependent: performance in anagram tests Control: same questions on test, same experimenter, same font and size

question

Wha is a confounding variable?

answer

General term for possible alternative explanation for a study's results

question

What are the three parts to causation?

answer

Covariance- one thing changes with the other Internal validity- any APES? Temporal precedence- Cause before effect

question

Describe random assignment and explain its role in establishing internal validity.

answer

The use of a random method (ex. Flipping a coin) to assign participants into different experimental designs; ensures that every participant in an experiment has an equal chance to be in each group. Use random assignment to avoid selection effects, results in fairly even distributions.

question

Is random assignment for between subjects or within subjects designs? Why?

answer

BSD because there is each person will go through the same testing

question

What is matching? What kinds of things might you match on?

answer

An experimental design technique in which participants who are similar on some measured variable are grouped into sets; the members of each matched set are then randomly assigned to different experimental conditions Things you might match: IQ if this will affect ability to perform tasks

question

Explain matching's role in establishing internal validity, and describe situations in which matching may be preferred to random assignment.

answer

Role in Internal Validity: Still done with random assignment and ensures that the groups are equal on some important variable (ex. IQ) before the manipulation of the independent variable ? takes care of selection effects Matching might be better when there is a smaller n and shared characteristics are more noticeable (ex. 6 people with high IQ ? 4 in Group 1, 1 in Group 2,1 in Group 3), but randomization is preferable.

question

When could matching be a problem?

answer

(1) Requires an extra step, requires many more resources than random assignment (2) Matching one variable can mean mismatch on another (3) Subject attrition: one or more subjects do not complete experiment or behavior changes not as result of experimental condition (can make groups unequal)

question

What are the procedures for independent-groups?

answer

(BSD) an experimental design in which different groups of participants are exposed to different levels of the independent variable. Two basic forms of independent groups design are the posttest-only design and the pretest/posttest design

question

What are the pros and cons for independent-groups?

answer

Pros: No chance of a treatment contaminating another Cons: Possibility that subjects in two groups have differences that influence effects of treatment

question

What are the procedures for within-groups experiments?

answer

Only one group of participants and all participate in all levels of the independent variable

question

What are the pros and cons for within-groups experiments?

answer

Pros: ensures the participants in the two groups will be equivalent and that the results are not due to individual difference, don't need as many participants; determine effect of treatment over time Cons: risk of carryover effects (toxicity, fatigue, practice effects) and other order effects, might not be practical

question

What is a posttest-only design?

answer

Participants are randomly assigned to independent variable level and are tested on the dependent variable once

question

Identify posttest-only designs' pros and cons

answer

Pros: simplest independent-groups design. Satisfy all three criteria for causation. Cons: combination of random assignment plus a manipulated variable can lead to powerful causal conclusions which researchers can usually be more confident of when using a pretest/posttest instead.

question

What is a pretest/posttest design used for?

answer

When researchers want to evaluate whether random assignment made the groups equal, used when the sample size is small; tracks how participants have improved over time in response to the manipulation

question

Identify pretest/posttest designs pros and cons

answer

Pros: Makes sure that the groups are equivalent Cons: Taking a baseline might affect the posttest. Pretest may make participants change their more spontaneous behavior.

question

What is the difference between a between-subjects design? Pros/Cons?

answer

Between-subjects: an experimental design in which different groups of participants are exposed to different levels of the independent variable

question

What is the difference between a within-subjects design? Pros/Cons?

answer

Only one group of participants and all participate in all levels of the independent variable

question

Explain the difference between concurrent-measures and repeated-measures designs.

answer

Concurrent-measures: participants are exposed to all the levels of an independent variable at roughly the same time, and a single attitudinal or behavioral preference is the dependent variable Repeated-measures: participants are measured on a dependent variable more than once-that is, after exposure to each level of the independent variable

question

What are carryover effects? How can you address them?

answer

Carryover effects: a type of order effect, in which some form of contamination carries over from one condition to the next (ex. Brushing your teeth and then drinking orange juice) Solution: Counterbalancing = the levels of the independent variable are presented to participants in different orders (ex. Some mothers played with their child first, others played with another's child first, then switched)

question

What are order effects?

answer

In a within-groups design, a threat to internal validity in which exposure to one condition changes participants' responses to a later condition (ex. Carryover effect, practice effect, fatigue effect, testing threat)

question

What is a Latin Square?

answer

Partial counterbalance that minimizes potential carryover effects, ensures that each condition appears in each position at least once.

question

How many possible combinations would there be in a variable with 5 levels?

answer

Possible combinations: 5x4x3x2x1 = 120

question

Describe counterbalancing, and explain its role in the internal validity of a within-groups design.

answer

The levels of the independent variable are presented to participants in different orders (ex. Some mothers played with their child first, others played with another's child first, then switched)

question

Interrogate the construct validity of the measured variable in an experiment.

answer

Measured variable (DV): how valid and reliable is the measure used. From Hannah's notes: Assess the quality of the operationalizations of the IV and DV based on the standard provided by the theory the study is testing (do the results of the study support your theory?)

question

Interrogate the construct validity of a manipulated variable in an experiment, and explain the role of manipulation checks and theory testing in establishing construct validity.

answer

Manipulated variable (IV): how well was the IV manipulated, face validity?, how has it been done before? Role of manipulation checks: an extra dependent variable that researchers can insert into an experiment to help them quantify how well an experiment manipulation worked (ex. Asking children how much effort and smartness contributed their ability to solve math problems) Role of theory testing: if the manipulation has been done well, then the dependent variable will yield results that will support the theory; collect additional data; does the manipulations and measures represent the intended constructs in the theory?

question

Interrogate two aspects of external validity for an experiment

answer

(1)External validity aspect: Generalizing to other people. Random sampling or convenience sampling? Taken from the population of interest? (2) External validity aspect: Generalizing to other settings. How well does the experimental situation represent other situations?

question

Explain why experimenters usually prioritize internal validity over external validity when it is difficult to achieve both.

answer

Internal validity: random assignment? NEED TO KNOW THAT THERE ARE NOT OTHER INFLUENCING VARIABLES; needed for a causal claim External validity: random sampling?

question

Identify effect size (d) and statistical significance and explain what they mean for an experiment.

answer

Effect size: The magnitude of a relationship between two or more variables; how far apart 2 experimental groups are on the dependent variable; difference between the means and the spread of scores within each group Statistical significance: when results are statistically significant, it is unlikely to have been obtained from chance (covariance!)

question

What are Cohen's guidelines for effect size strength?

answer

0.20 = small or weak 0.50 = medium or moderate 0.80 = large or strong

question

What are the three threats to internal validity?

answer

Design confounds Selection effects Order effects

question

Define Design confounds

answer

• A poorly designed experiment • The confound varies along with independent variable in a systematic way (so would be an alternative plausible explanation for the results)

question

Define Selection effects

answer

• Experiment has different types of participants • Participants in one group (or one level of I.V.) are different in some way from participants in the other groups (ex: self selection)

question

Define Order effects

answer

• Outcome might be caused by the order in which the levels of the IV are presented • In a within-groups design, exposure to one condition changes participants' responses to a later condition (participants are getting tired, bored, or well-practiced) (ex. carryover effects, practice effects, etc.)

question

What are the NINE threats to internal validity?

answer

History Maturation Regression (to the mean) Attrition Testing Instrumentation Observer bias Demand characteristics Placebo effects

question

Maturation

answer

A change in behavior that emerges more or less spontaneously over time Solution: Have an appropriate comparison group (a group in an experiment whose level on the IV differs from those of the treatment group in some intended and meaningful way

question

History

answer

An external event that affects most/all members in the study - at the time of the treatment Solution: Comparison group

question

Regression

answer

When a performance is extreme at Time 1, the performance is likely to be less extreme at Time 2 (closer to a typical or average performance) Solution: Comparison group (to rule out regression, even if the comparison and treatment group started out equally extreme, their change in the DV would be a different rates)

question

Attrition

answer

When a certain kind of participant drops out of a study for some systematic reason Solution: (1) Remove the pretest scores of the participants who dropped out (from the pretest average) and (2) check the pretest scores of the dropouts

question

Testing

answer

Kind of order effect in which participants tend to change as a result of having been tested before Solution: (1) Use a posttest-only design. (2) If pretest-posttest design is needed, use alternative forms of the test. (3) Use a comparison group.

question

Instrumentation

answer

When a measuring instrument changes over repeated use (ex. graders change their standards over time (more strict or more lenient) and may cause for participants to appear to have changed) OR (2) the alternative forms of the test are not sufficiently equivalent Solution: (1) Use a posttest-only design. (2) If pretest-posttest design is needed, the pre and posttest measures need to be equivalent. (3) Establish coders reliability and validity at pre and posttest (use clear coding manuals). (4) Counterbalance the versions of the test

question

Observer Bias

answer

When experimenter's expectations influence their interpretation of the results which threatens internal validity (APEs) and construct validity (ratings do not represent true levels of the construct) Solution: (1) Double-blind study (neither the participants nor the researchers who evaluate then know who is in the treatment group and who is in the comparison group) OR (2) masked design/blind study (participants know which group they are in, but the observers do not)

question

Demand Characteristics

answer

When participants guess what the study is about and change their behavior in the expected direction Solution: (1) Double-blind study OR (2) Masked design/blind study

question

Placebo Effect

answer

When participants improve but only because they believe they are receiving an effective treatment (1) Double-blind placebo control study (neither the people treating the patients not the patients themselves know whether they are in the real treatment group or the placebo group); (2) To definitively show a placebo effect requires a treatment group, a placebo treatment group, and a no-treatment at all group

question

Articulate the reasons that a study might result in null effects

answer

Not enough variance between groups: Too much variance within groups: A true null effect:

question

Describe three causes of within-group variance and indicate how each might be reduced.

answer

Measurement error: Solution: Individual differences: Solution: Situation noise: Solution:

question

Explain reasons to conduct a factorial study

answer

• Multifactor experiments more likely to have ecological validity than single-factor experiments. • Increase generality if experiment accounts for complex forces. • Explanation is a developmental process from simple experiments to complex experiments

question

What are interactions? Why might they be important?

answer

Interactions occur when the effect of one I.V. depends on the level of another I.V.

question

Know the matrix we talked about

answer

• A 2x2 can only have one interaction or zero interaction. • If on a graph, the slopes of each line are the same, there is no interaction.

question

What is a moderator?

answer

A Moderator is an independent variable (I.V.) that changes the relationship between another I.V. and a D.V. The Moderator results in an interaction

question

Review studies with one independent variable, which show a simple "difference."

answer

In a simple 1 IV and 1 DV experiment we are looking for a difference. Does talking on a cell phone (IV) result in worse driving (DV)?

question

Describe an interaction as a "difference in differences."

answer

This was the example where they asked if having a large bottle (on sale or not) of a product would increase the amount used verse a small bottle (on sale or not) of the same product. (We used laundry detergent as the product in class)

question

Describe interactions in terms of "it depends."

answer

This was the example where they tested whether individuals memory would improve from different learning conditions (water's edge/underwater) and where they recalled it (water's edge/underwater). The question that was asked was "Do people recall material better on land or underwater? It depends on where they learned the material."

question

Given a factorial notation (e.g., 2 × 3), identify the number of independent variables, the number of levels of each variable, the number of cells in the design, and the number of main effects and interactions that will be relevant?

answer

There are 2 IV's, (one with three levels, one with two) There are 6 cells of the I.V.s Number of main effects 3

question

Explain the basic logic of three-way factorial designs.

answer

Example given in class: comparing drivers age (old/young) ability to hit the breaks compared to how they are interacting with their cell phones (Hands-free/Hand-held/No phone).

question

What is a mixed design?

answer

Is used to test for differences between two or more independent groups whilst subjecting participants to repeated measures.

question

Determine, from a graph, whether a study shows a three-way interaction.

answer

Example given in class: comparing drivers age (old/young) ability to hit the breaks compared to how they are interacting with their cell phones (Hands-free/Hand-held/No phone) and traffic conditions (heavy/light). If you graph the results, if the slopes of any of the IV's are different, there is an interaction.

question

What are the key words that indicate factorial design language in a journal article?

answer

• Interaction: may exhibit an interaction • Main effect: the effect of an independent variable on a dependent variable averaging across the levels of any other independent variables. • Significant: p ; 0.05

question

Interpret keywords in popular press articles that indicate a factorial design.

answer

• "It Depends" statements: Used to highlight interactions in a factorial design. • Look for participant variable (age, gender, ethnicity)

question

Explain how quasi-experiments can be either independent-groups designs or within-groups designs.

answer

Quasi-experiments are where you do not have full experimental control.

question

Define the following nonequivalent control group design, interrupted time-series design, and nonequivalent control groups interrupted time-series design

answer

A quasi-experimental study that has at least one treatment group and one comparison group. Participants have not been randomly assigned to the two groups (ex: head start program where kids were assigned to a group based on their family economics)

question

Define the following interrupted time-series design, and nonequivalent control groups interrupted time-series design

answer

Study that measures participants repeated on a dependent variable before, during, and after the "interruption" caused by some event (ex: parole decision making before, during, and after an interruption (food break))

question

Define the following nonequivalent control groups interrupted time-series design

answer

Combines to previous designs. Independent variables are studied both as a repeated-measures variable (ITS) and as an independent-group variable (NECG).

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Selection

answer

Relevant only for independent group designs. Internal validity threat applies when the groups at the various levels of an IV contain different types of participants.

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Maturation

answer

Occurs when in an experimental or quasi-experimental design, with a pretest and posttest, is not clear when improvement was caused by treatment or if they would have improved spontaneously without it.

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: History

answer

Occurs when an external event happens for everyone in the study.

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Regression

answer

Occurs when an extreme finding is caused by a combination of random factors that are unlikely to happen in the same combination again. The more extreme the scores, the more likely the scores will draw closer to the mean if tested again.

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Attrition

answer

When people drop out of a study for some systematic reason.

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Testing

answer

Kind of order effect in which participants tend to change as a result of having been tested before

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Instrumentation

answer

When a measuring instrument changes over repeated use (ex: graders change their standards over time and may cause for participants to appear to have changed)

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Observer Bias

answer

When experimenter's expectations influence their interpretation of the results.

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Experimental Demand

answer

When participants guess what the study is about and change their behavior in the expected direction

question

Explain whether quasi-experimental studies avoid the following threats to internal validity: Placebo effects

answer

When participants improve but only because they believe they are receiving an effective treatment.

question

Using both the design and the results, analyze whether a quasi-experimental design allows you to rule out internal validity threats.

answer

Most of these threats can be ruled out by other studies

question

Explain the tradeoffs of using a quasi-experimental design.

answer

• Quasi-experimental designs enable researcher to take advantage of real-world opportunities to study interesting phenomena and important events. • Can enhance external validity in with the likelihood that patterns observed in the quasi-experiment will generalize to other settings and individuals. • Ethically, people use quasi-experiments because it would be unethical to randomly assign individuals to be in a certain situation.

question

Interrogate quasi-experimental designs by asking about construct validity, external validity, and statistical validity.

answer

Construct: Interrogate how successfully the study manipulated or measure its variables (IV and DV). External: You don't have to ask whether the judicial decisions of making study applies to real-world settings because the study occurred in a real-world setting. Might want to ask if we can generalize it to other demographics/populations. Statistical: know how large the group differences are (the effect size) and whether the results are statistically different.

question

What are case studies?

answer

Long-term treatment (or experiment) on individual, obtain measurement of person's thought and action after the fact (e.g. H.M.)

question

Explain three differences between small-N and large-N experiments.

answer

Large N: Participants are grouped. The data from an individual participant are not of interest in themselves; data from all participants in each group are combined and studied together. Data are represented as group averages Small N: Each participant is treated as a separate experiment. Are almost always repeated measures designs, in which researchers observe how the person or animal responds to several systematically designed conditions. Individuals data are presented.

question

Describe the small-N design: Stable-baseline designs

answer

Study in which a researcher observes behavior for an extended baseline period before beginning a treatment or other intervention. If behavior is stable during the baseline, the researcher is more certain of the treatment's effectiveness. (ex: Alzheimer's patient)

question

Describe the small-N design: Multiple-baseline designs

answer

This is where researchers stagger their introduction of an intervention across a variety of contexts, times, or situations. (ex: special needs girl with three undesired behaviors)

question

Describe the small-N design: Reversal designs

answer

Observes behavior both with and without treatment but takes the treatment away for awhile (reversal period) to see whether the problem behavior returns (reverses). Can make a causal statement if the treatment was really working the behavior should worsen again when the treatment is discontinued.

question

Give examples of questions you would ask about a small-N design to interrogate all four big validities.

answer

Internal Validity: How can I enhance internal validity. Within subject experiments allow us to draw causal conclusions. External Validity: How can one person represent a population? Can minimize threat to external validity by: (1) triangulate by combining the results of a single-n study with other studies on animals or larger groups. (2) researchers can specify the population to which they want to generalize (3) some researchers are not concerned about generalizing at all. Even if it applies to one person, it is still useful. Construct validity: do they have multiple observers and interrater reliability? Statistical: how did they treat their data? What about the effect sizes? By what margin did the clients behavior improve?

question

Explain the trade-offs of using a small-N design.

answer

Few participants may not represent human population

question

What about age as a variable?

answer

• Age is confounded with generation of birth. Each generation has its own attitudes, values, unique experiences, even health issues, that can influence behavior. • With longitudinal methods, generation (cohort) factors is not a factor. Longitudinal method confounds age with time of treatment. However, not only does age change, but the world has changed too; so was the difference due to age or to changes in environment?

question

Know the difference between time lag, cross-sectional, cross-sequential, and longitudinal studies

answer

Time Lag: looking at the effects on 19 yr olds born at different times and tested in different years to minimize those effects Cross-sectional: select people of different ages and randomly assign half of each age group to one of experimental conditions. (between subjects design. Ex: compare 7 year olds to 12 year olds) Cross-sequential: testing two or more age groups at two or more time periods (this is like a mixed design, both within subjects and between subjects) Longitudinal: follow a participant along the age dimension (within subjects)

Psych 310: Exam 2 – Flashcards

Unlock all answers in this set

Haven't found what you were looking for?

Search for samples, answers to your questions and flashcards